{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T14:08:28Z","timestamp":1758636508096,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031724367"},{"type":"electronic","value":"9783031724374"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-72437-4_15","type":"book-chapter","created":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T20:41:19Z","timestamp":1727296879000},"page":"256-272","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["LIAS: Layout Information-Based Article Separation in\u00a0Historical Newspapers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7857-8737","authenticated-orcid":false,"given":"Wenjun","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5993-1630","authenticated-orcid":false,"given":"Hanh Thi Hong","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0787-2990","authenticated-orcid":false,"given":"Carlos-Emiliano","family":"Gonz\u00e1lez-Gallardo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0123-439X","authenticated-orcid":false,"given":"Micka\u00ebl","family":"Coustaty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6160-3356","authenticated-orcid":false,"given":"Antoine","family":"Doucet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,26]]},"reference":[{"issue":"3","key":"15_CR1","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s10032-021-00380-6","volume":"24","author":"S Biswas","year":"2021","unstructured":"Biswas, S., Riba, P., Llad\u00f3s, J., Pal, U.: Beyond document object detection: instance-level segmentation of complex layouts. Int. J. Doc. Anal. Recogn. (IJDAR) 24(3), 269\u2013281 (2021)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Boro\u015f, E., et al.: Alleviating digitization errors in named entity recognition for historical documents. In: Proceedings of the 24th Conference on Computational Natural Language Learning, pp. 431\u2013441 (2020)","DOI":"10.18653\/v1\/2020.conll-1.35"},{"key":"15_CR3","unstructured":"Doucet, A., et\u00a0al.: NewsEye: a digital investigator for historical newspapers. In: 15th Annual International Conference of the Alliance of Digital Humanities Organizations, DH 2020 (2020)"},{"issue":"1","key":"15_CR4","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1145\/361237.361242","volume":"15","author":"RO Duda","year":"1972","unstructured":"Duda, R.O., Hart, P.E.: Use of the Hough transformation to detect lines and curves in pictures. Commun. ACM 15(1), 11\u201315 (1972)","journal-title":"Commun. ACM"},{"issue":"2","key":"15_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3604931","volume":"56","author":"M Ehrmann","year":"2023","unstructured":"Ehrmann, M., Hamdi, A., Pontes, E.L., Romanello, M., Doucet, A.: Named entity recognition and classification in historical documents: a survey. ACM Comput. Surv. 56(2), 1\u201347 (2023)","journal-title":"ACM Comput. Surv."},{"key":"15_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1007\/978-3-030-58219-7_21","volume-title":"Experimental IR Meets Multilinguality, Multimodality, and Interaction","author":"M Ehrmann","year":"2020","unstructured":"Ehrmann, M., Romanello, M., Fl\u00fcckiger, A., Clematide, S.: Overview of CLEF HIPE 2020: named entity recognition and linking on historical newspapers. In: Arampatzis, A., et al. (eds.) CLEF 2020. LNCS, vol. 12260, pp. 288\u2013310. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58219-7_21"},{"key":"15_CR7","doi-asserted-by":"publisher","unstructured":"Girdhar, N., Coustaty, M., Doucet, A.: Benchmarking NAS for article separation in historical newspapers. In: Goh, D.H., Chen, S.J., Tuarob, S. (eds.) ICADL 2023. LNCS, vol. 14457, pp. 76\u201388. Springer, Singapore (2023). https:\/\/doi.org\/10.1007\/978-981-99-8085-7_7","DOI":"10.1007\/978-981-99-8085-7_7"},{"key":"15_CR8","doi-asserted-by":"publisher","unstructured":"Girdhar, N., Coustaty, M., Doucet, A.: STRAS: a semantic textual-cues leveraged rule-based approach for article separation in historical newspapers. In: Goh, D.H., Chen, S.J., Tuarob, S. (eds.) ICADL 2023. LNCS, vol. 14457, pp. 89\u2013105. Springer, Singapore (2023). https:\/\/doi.org\/10.1007\/978-981-99-8085-7_8","DOI":"10.1007\/978-981-99-8085-7_8"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez-Gallardo, C.E., Boros, E., Girdhar, N., Hamdi, A., Moreno, J.G., Doucet, A.: Yes but.. can ChatGPT identify entities in historical documents? In: The ACM\/IEEE-CS Joint Conference on Digital Libraries, pp. 184\u2013189 (2023)","DOI":"10.1109\/JCDL57899.2023.00034"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Gr\u00fcning, T., Labahn, R., Diem, M., Kleber, F., Fiel, S.: READ-BAD: a new dataset and evaluation scheme for baseline detection in archival documents. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 351\u2013356. IEEE (2018)","DOI":"10.1109\/DAS.2018.38"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Gu, Z., et al.: XYLayoutLM: towards layout-aware multimodal networks for visually-rich document understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4583\u20134592 (2022)","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Hong, T., Kim, D., Ji, M., Hwang, W., Nam, D., Park, S.: BROS: a pre-trained language model focusing on text and layout for better key information extraction from documents. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 10767\u201310775 (2022)","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document AI with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"15_CR14","unstructured":"Lee, J., Han, J., Baek, S., Song, M.: Topic segmentation model focusing on local context. In: AAAI-23 Workshop Program (2023)"},{"key":"15_CR15","unstructured":"Schweter, S., M\u00e4rz, L., Schmid, K., \u00c7ano, E.: hmBERT: historical multilingual language models for named entity recognition. In: Conference and Labs of the Evaluation Forum (CLEF 2020) (2022)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Wang, J., Jin, L., Ding, K.: LiLT: a simple yet effective language-independent layout transformer for structured document understanding. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7747\u20137757 (2022)","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 2579\u20132591 (2021)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"}],"container-title":["Lecture Notes in Computer Science","Linking Theory and Practice of Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72437-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T05:04:53Z","timestamp":1731647093000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72437-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031724367","9783031724374"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72437-4_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"26 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare relevant to this article\u2019s content","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"TPDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Theory and Practice of Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpdl2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tpdl2024.nuk.si\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}